In-cabin detection framework

1. A method, comprising: scanning a cabin of a vehicle via a scanning device to generate a scan, wherein the scan includes image data of a spatial region inside the vehicle and outside the vehicle proximate at least one vehicle door; transmitting the scan from the scanning device to a hardware system within the vehicle via a controller area network (CAN) bus of the vehicle; executing a neural network on the scan via the hardware system within the vehicle, wherein the execution of the neural network simultaneously determines a per seat prediction of presence of life and a per seat prediction of whether the presence of life is a child, and outputs a Boolean indicator of the per seat prediction of presence of life and another Boolean indicator of the per seat prediction of whether a child is present; transmitting information about the least one seat and the at least one footwell per seat prediction of presence of life and the per seat prediction of whether the presence of life is a child to a communication module of the vehicle via the CAN bus; and wirelessly communicating the information about the per seat prediction of presence of life and the per seat prediction of whether the presence of life is a child to a mobile device via the communication module.

2. The method of claim 1 wherein the simultaneously determining comprises simultaneously determining a per seat prediction of presence within a footwell of the vehicle.

3. The method of claim 1 wherein the scan captures at least one point cloud center of the at least one of a footwell and a head space of the cabin.

4. The method of claim 1 wherein the scan utilizes predefined cuboid boundaries for the at least one seat inside the vehicle to determine a spatial occupancy and a seat specific occupancy.

5. The method of claim 1 further comprising communicating logs of the scan via the CAN bus to a server, wherein the server updates a cabin status model based on the logs of the scan.

6. A system, comprising: a processor configured to: scan a cabin of a vehicle via a scanning device, wherein the scan includes image data of a spatial region inside the vehicle and outside the vehicle proximate at least one vehicle door; transmit the scan from the scanning device to a hardware system within the vehicle via a controller area network (CAN) bus of the vehicle; execute a neural network on the scan via the hardware system within the vehicle, wherein the execution of the neural network simultaneously determines a per seat prediction of presence of life and a per seat prediction of whether the presence of life is a child, and outputs a Boolean indicator of the per seat prediction of presence of life and another Boolean indicator of the per seat prediction of whether a child is present; transmit information about the per seat prediction of presence of life and the per seat prediction of whether the presence of life is a child to a communication module of the vehicle via the CAN bus; and wirelessly communicate information about the per seat prediction of presence of life and the per seat prediction of whether the presence of life is a child to a mobile device via the communication module.

7. The system of claim 6, wherein the processor is configured to determine that a per seat prediction of presence within a footwell of the vehicle.

8. The system of claim 6, wherein the scan captures at least one point cloud center of the at least one footwell and a head space of the cabin.

9. The system of claim 6, wherein the scan utilizes predefined cuboid boundaries for the at least one seat inside the vehicle to determine a spatial occupancy and a seat specific occupancy.

10. The system of claim 6, wherein the processor is configured to communicate logs of the scan via the CAN bus to a server, wherein the server updates a cabin status model based on the logs of the scan.

11. A non-transitory computer-readable medium comprising instructions, that when read by a processor, cause the processor to perform: scanning a cabin of a vehicle via a scanning device to generate a scan, wherein the scan includes image data of a spatial region inside the vehicle and outside the vehicle proximate at least one vehicle door; transmitting the scan from the scanning device to a hardware system within the vehicle via a controller area network (CAN) bus of the vehicle; executing a neural network on the scan via the hardware system within the vehicle, wherein the execution of the neural network simultaneously determines a per seat prediction of presence of life and a per seat prediction of whether the presence of life is a child, and outputs a Boolean indicator of the per seat prediction of presence and another Boolean indicator of the per seat prediction of whether a child is present; transmitting information about the per seat prediction of presence of life and the per seat prediction of whether the presence of life is a child to a communication module of the vehicle via the CAN bus; and wirelessly communicating the information about the per seat prediction of presence of life and the per seat prediction of whether the presence of life is a child to a mobile device via the communication module.

12. The non-transitory computer-readable medium of claim 11, wherein the simultaneously determining comprises simultaneously determining a per seat prediction of presence within a footwell of the vehicle.

13. The non-transitory computer-readable medium of claim 11, wherein the scan captures at least one point cloud center of the at least one footwell and a head space of the cabin.

14. The non-transitory computer-readable medium of claim 11, wherein the scan utilizes predefined cuboid boundaries for the at least one seat inside the vehicle to determine a spatial occupancy and a seat specific occupancy.